In this part, we will analyze copy number signatures across cancer types and show the landscape.
Signature number and contribution in each cancer type
Load tidy cancer type annotation data.
library(sigminer)
library(tidyverse)
pcawg_types <- readRDS("../data/pcawg_type_info.rds")Load signature activity data.
pcawg_activity <- readRDS("../data/pcawg_cn_sigs_CN176_activity.rds")Combine the cancer type annotation and activity data and only keep samples with good reconstruction (>0.75 cosine similarity).
keep_samps <- pcawg_activity$similarity[similarity > 0.75]$sample
df_abs <- merge(pcawg_activity$absolute[sample %in% keep_samps], pcawg_types, by = "sample")
df_rel <- merge(pcawg_activity$relative[sample %in% keep_samps], pcawg_types, by = "sample")Signature activity in each cancer type
Here we draw distribution of a signature across cancer types.
show_group_distribution(
df_abs,
gvar = "cancer_type",
dvar = "CNS1",
order_by_fun = FALSE,
g_angle = 90,
point_size = 0.3
)
We have many signatures here, so we output them to PDF files.
dir.create("../output/cancer-type-dist", showWarnings = F)
signames <- paste0("CNS", 1:14)
for (i in signames) {
pxx <- show_group_distribution(df_abs,
gvar = "cancer_type",
dvar = i, order_by_fun = FALSE,
ylab = i,
g_angle = 90, point_size = 0.3
)
ggplot2::ggsave(file.path("../output/cancer-type-dist/", paste0("Absolute_activity_", i, ".pdf")),
plot = pxx, width = 12, height = 6
)
pxx <- show_group_distribution(df_rel,
gvar = "cancer_type",
dvar = i, order_by_fun = FALSE,
ylab = i,
g_angle = 90, point_size = 0.3
)
ggplot2::ggsave(file.path("../output/cancer-type-dist/", paste0("Relative_activity_", i, ".pdf")),
plot = pxx, width = 12, height = 6
)
}
rm(pxx)Signature landscape
Define a signature which is detectable if this signature contribute >5% exposures and contribute >15 segments in a sample.
df <- df_rel %>%
dplyr::mutate_at(dplyr::vars(dplyr::starts_with("CNS")), ~ ifelse(. > 0.05, 1L, 0L)) %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("CNS"),
names_to = "sig", values_to = "detectable"
)
df2 <- df_rel %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("CNS"),
names_to = "sig", values_to = "expo"
)
df3 <- df_abs %>%
dplyr::mutate_at(dplyr::vars(dplyr::starts_with("CNS")), ~ ifelse(. > 15, 1L, 0L)) %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("CNS"),
names_to = "sig", values_to = "segment_detect"
)
df <- dplyr::left_join(df, df2,
by = c("sample", "cancer_type", "sig")
) %>% dplyr::left_join(., df3, by = c("sample", "cancer_type", "sig"))
df_type <- df %>%
dplyr::group_by(cancer_type, sig) %>%
dplyr::summarise(
freq = sum(segment_detect), # directly use count
expo = median(expo[detectable == 1]),
n = n(),
label = paste0(unique(cancer_type), " (n=", n, ")"),
.groups = "drop"
) %>%
dplyr::group_by(cancer_type) %>%
dplyr::mutate(pro = freq / sum(freq))
df_type$expo <- ifelse(df_type$freq == 0, 0, df_type$expo)
mps <- unique(df_type[, c("cancer_type", "label")])
mpss <- mps$label
names(mpss) <- mps$cancer_typesummary(df_type$freq) Min. 1st Qu. Median Mean 3rd Qu. Max.
0.00 1.00 7.00 15.27 20.00 175.00 Show copy number signature landscape.
library(cowplot)
p <- ggplot(
df_type,
aes(x = cancer_type, y = factor(sig, levels = paste0("CNS", 1:14)))
) +
geom_point(aes(size = pro, color = expo)) +
theme_cowplot() +
ggpubr::rotate_x_text(60) +
scale_x_discrete(breaks = mps$cancer_type, labels = mps$label) +
scale_size_continuous(
limits = c(0.1, 1),
breaks = c(0, 0.25, 0.5, 0.75, 1)
) +
scale_color_stepsn(
colors = viridis::viridis(5, direction = -1),
breaks = c(0, 0.25, 0.5, 0.75, 1)
) +
labs(
x = NULL, y = "Copy number signatures",
color = "Median activity\ndue to signature",
size = "Proportion of tumors \nwith the signatures"
)
p
### Signature number distribution
For most of cancer types, they have similar signature constitution (most of copy number signatures available in them). However, we need to further check that if many tumors have so many signatures activated.
pcawg_cns <- readRDS("../data/pcawg_cn_sigs_CN176_signature.rds") %>%
.[["Exposure.norm"]] %>%
t() %>%
as.data.frame() %>%
tibble::rownames_to_column(., var = "sample")
pcawg_sbs <- read_csv("../data/PCAWG/PCAWG_sigProfiler_SBS_signatures_in_samples.csv")
pcawg_dbs <- read_csv("../data/PCAWG/PCAWG_sigProfiler_DBS_signatures_in_samples.csv")
pcawg_id <- read_csv("../data/PCAWG/PCAWG_SigProfiler_ID_signatures_in_samples.csv")
# Use signature relative contribution for analysis
pcawg_sbs <- pcawg_sbs[, -c(1, 3)] %>%
dplyr::rename(sample = `Sample Names`) %>%
dplyr::select(-SBS43, -c(SBS45:SBS60))
pcawg_dbs <- pcawg_dbs[, -c(1, 3)] %>%
dplyr::rename(sample = `Sample Names`)
pcawg_id <- pcawg_id[, -c(1, 3)] %>%
dplyr::rename(sample = `Sample Names`)
df_cns <- df_rel %>%
dplyr::mutate_at(dplyr::vars(dplyr::starts_with("CNS")), ~ ifelse(. > 0.05, 1L, 0L)) %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("CNS"),
names_to = "sig", values_to = "detectable"
)
df2_cns <- df_rel %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("CNS"),
names_to = "sig", values_to = "expo"
)
df3_cns <- df_abs %>%
dplyr::mutate_at(dplyr::vars(dplyr::starts_with("CNS")), ~ ifelse(. > 15, 1L, 0L)) %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("CNS"),
names_to = "sig", values_to = "segment_detect"
)
df_cns <- dplyr::left_join(df_cns, df2_cns,
by = c("sample", "cancer_type", "sig")
) %>% dplyr::left_join(., df3_cns, by = c("sample", "cancer_type", "sig"))
df_type_cns <- df_cns %>%
dplyr::group_by(cancer_type, sig) %>%
dplyr::summarise(
freq = sum(segment_detect), # directly use count
expo = median(expo[detectable == 1]),
n = n(),
label = paste0(unique(cancer_type), " (n=", n, ")"),
.groups = "drop"
)
mps <- unique(df_type_cns[, c("cancer_type", "label")])
mpss <- mps$label
names(mpss) <- mps$cancer_type
df_detc_cns <- df_cns %>%
dplyr::group_by(cancer_type, sample) %>%
dplyr::summarise(
signumber = sum(segment_detect),
.groups = "drop"
)
num_CNS <- df_detc_cns$signumber
# SBS
pcawg_sbs2 <- dplyr::inner_join(pcawg_sbs,
df_rel[, c("sample", "cancer_type")],
by = "sample"
)
df_sbs <- pcawg_sbs2 %>%
dplyr::mutate_at(dplyr::vars(dplyr::starts_with("SBS")), ~ ifelse(. > 0, 1L, 0L)) %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("SBS"),
names_to = "sig", values_to = "detectable"
)
df2_sbs <- pcawg_sbs2 %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("SBS"),
names_to = "sig", values_to = "expo"
)
df_sbs <- dplyr::left_join(df_sbs, df2_sbs,
by = c("sample", "cancer_type", "sig")
)
df_type_sbs <- df_sbs %>%
dplyr::group_by(cancer_type, sig) %>%
dplyr::summarise(
freq = sum(detectable), # directly use count
expo = median(expo[detectable == 1]),
n = n(),
label = paste0(unique(cancer_type), " (n=", n, ")"),
.groups = "drop"
)
df_detc_sbs <- df_sbs %>%
dplyr::group_by(cancer_type, sample) %>%
dplyr::summarise(
signumber = sum(detectable),
.groups = "drop"
)
num_SBS <- df_detc_sbs$signumber
# DBS
pcawg_dbs2 <- dplyr::inner_join(pcawg_dbs,
df_rel[, c("sample", "cancer_type")],
by = "sample"
)
df_dbs <- pcawg_dbs2 %>%
dplyr::mutate_at(dplyr::vars(dplyr::starts_with("DBS")), ~ ifelse(. > 0, 1L, 0L)) %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("DBS"),
names_to = "sig", values_to = "detectable"
)
df2_dbs <- pcawg_dbs2 %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("DBS"),
names_to = "sig", values_to = "expo"
)
df_dbs <- dplyr::left_join(df_dbs, df2_dbs,
by = c("sample", "cancer_type", "sig")
)
df_type_dbs <- df_dbs %>%
dplyr::group_by(cancer_type, sig) %>%
dplyr::summarise(
freq = sum(detectable), # directly use count
expo = median(expo[detectable == 1]),
n = n(),
label = paste0(unique(cancer_type), " (n=", n, ")"),
.groups = "drop"
)
df_detc_dbs <- df_dbs %>%
dplyr::group_by(cancer_type, sample) %>%
dplyr::summarise(
signumber = sum(detectable),
.groups = "drop"
)
num_DBS <- df_detc_dbs$signumber
# ID
# DBS
pcawg_id2 <- dplyr::inner_join(pcawg_id,
df_rel[, c("sample", "cancer_type")],
by = "sample"
)
df_id <- pcawg_id2 %>%
dplyr::mutate_at(dplyr::vars(dplyr::starts_with("ID")), ~ ifelse(. > 0, 1L, 0L)) %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("ID"),
names_to = "sig", values_to = "detectable"
)
df2_id <- pcawg_id2 %>%
tidyr::pivot_longer(
cols = dplyr::starts_with("ID"),
names_to = "sig", values_to = "expo"
)
df_id <- dplyr::left_join(df_id, df2_id,
by = c("sample", "cancer_type", "sig")
)
df_type_id <- df_id %>%
dplyr::group_by(cancer_type, sig) %>%
dplyr::summarise(
freq = sum(detectable), # directly use count
expo = median(expo[detectable == 1]),
n = n(),
label = paste0(unique(cancer_type), " (n=", n, ")"),
.groups = "drop"
)
df_detc_id <- df_id %>%
dplyr::group_by(cancer_type, sample) %>%
dplyr::summarise(
signumber = sum(detectable),
.groups = "drop"
)
num_ID <- df_detc_id$signumber
# sum
df_num_all <- dplyr::tibble(
sig_type = rep(
c("CNS", "SBS", "DBS", "ID"),
c(length(num_CNS), length(num_SBS), length(num_DBS), length(num_ID))
),
num = c(num_CNS, num_SBS, num_DBS, num_ID)
)
# saveRDS(df_num_all, file = "/home/tzy/projects/CNX-method/data/df_num_all.rds")Pan-Cancer signature number distribution.
library(ggpubr)
num <- ggboxplot(df_num_all,
x = "sig_type", y = "num",
ylab = "Signature number",
color = "sig_type",
xlab = FALSE,
legend = "none",
palette = "jco",
width = 0.3,
outlier.size = 0.05
) +
scale_color_manual(values = c("#0073C2", "#EFC000", "#CD534C", "#7AA6DC"))
num
Most tumors have 3-6 signatures.
cancer_num <- ggplot(data = df_detc_cns, aes(x = cancer_type, y = signumber, fill = cancer_type)) +
geom_boxplot() +
coord_flip() +
labs(x = NULL, y = "Signature number") +
theme_cowplot() +
theme(legend.position = "none")
cancer_num
From the landscape and distribution data, we know that many signatures activate in most of cancer types, but for a specified tumor, in general there are 2-4 signatures are detectable.
Cancer type associated enrichment
Run enrichment analysis.
enrich_result <- group_enrichment(
df_abs,
grp_vars = "cancer_type",
enrich_vars = paste0("CNS", 1:14),
co_method = "wilcox.test"
)Show enrichment landscape.
enrich_result$enrich_var <- factor(enrich_result$enrich_var, paste0("CNS", 1:14))
p <- show_group_enrichment(enrich_result, fill_by_p_value = TRUE, return_list = T)
p <- p$cancer_type + labs(x = NULL, y = NULL)
p
ggsave("../output/CNS_PCAWG_enrichment_landscape.pdf",
plot = p,
height = 8, width = 8.5
)To better visualize the enrichment results, we use binned color regions.
p <- show_group_enrichment(
enrich_result,
fill_by_p_value = TRUE,
cut_p_value = TRUE,
return_list = T
)
p <- p$cancer_type + labs(x = NULL, y = NULL)
p
ggsave("../output/CNS_PCAWG_enrichment_landscape2.pdf",
plot = p,
height = 8, width = 8.5
)We see cancer type SoftTissue-Liposarc has pretty high enrichment on CNS4. Let’s check the enrichment result.
enrich_result[grp1 == "SoftTissue-Liposarc"] grp_var enrich_var grp1 grp2 grp1_size grp1_pos_measure
1: cancer_type CNS1 SoftTissue-Liposarc Rest 19 96.315789
2: cancer_type CNS2 SoftTissue-Liposarc Rest 19 68.736842
3: cancer_type CNS3 SoftTissue-Liposarc Rest 19 11.947368
4: cancer_type CNS4 SoftTissue-Liposarc Rest 19 435.526316
5: cancer_type CNS5 SoftTissue-Liposarc Rest 19 17.684211
grp2_size grp2_pos_measure measure_observed measure_tested p_value
1: 2718 15.318985 6.2873482 NA 7.503689e-07
2: 2718 13.663355 5.0307439 NA 1.832154e-02
3: 2718 12.660412 0.9436793 NA 8.258332e-01
4: 2718 8.231052 52.9125928 NA 1.535689e-22
5: 2718 10.408389 1.6990344 NA 6.439534e-02
type method fdr
1: continuous wilcox.test 1.715129e-06
2: continuous wilcox.test 2.664952e-02
3: continuous wilcox.test 8.258332e-01
4: continuous wilcox.test 4.914204e-21
5: continuous wilcox.test 8.586046e-02
[ reached getOption("max.print") -- omitted 9 rows ]Let’s go further plot the distribution for the two groups.
df_check <- df_abs[, c("CNS4", "cancer_type")][
, .(
cancer_type = ifelse(cancer_type == "SoftTissue-Liposarc",
"SoftTissue-Liposarc",
"Others"
),
CNS4 = CNS4
)
]# ggpubr::ggboxplot(
# df_check,
# x = "cancer_type", y = "CNS4",
# fill = "cancer_type",
# xlab = FALSE, width = 0.3, legend = "none")
show_group_distribution(
df_check,
gvar = "cancer_type",
dvar = "CNS4",
order_by_fun = FALSE,
g_angle = 90,
ylab = "CNS4"
)
Check copy number distribution for the "SoftTissue-Liposarc" samples.
samples <- df_abs[cancer_type == "SoftTissue-Liposarc"]$sample
pcawg_cn_obj <- readRDS("../data/pcawg_cn_obj.rds")
cn_dt <- subset(pcawg_cn_obj@data, sample %in% samples)
cn_dt$segLen <- cn_dt$end - cn_dt$start + 1Copy number value:
boxplot(cn_dt$segVal, ylab = "Copy number value")
Segment length:
boxplot(cn_dt$segLen, ylab = "Segment length")
cn_dt_samp <- cn_dt[, .(nAMP = sum(segVal > 2)), by = sample]boxplot(cn_dt_samp$nAMP, ylab = "Number of amplifications")